Do I need to initialize the Redis database first? about chatgpt-memory HOT 4 CLOSED

I create a Redis stack database and enter host, port, password etc in .env file.
all the scripts under ./tests/ passed with no problem.

from chatgpt-memory.

I'm basically stuck with the same issue, except I'm using Linux / Debian 12 and Python 3.11.2 in a virtual environment

$ poetry run uvicorn rest_api:app --host 0.0.0.0 --port 8000
Traceback (most recent call last):
File "/home/martin/src/chatgpt-memory/gpt-memory/bin/uvicorn", line 8, in
sys.exit(main())
^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/click/core.py", line 1157, in call
return self.main(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/click/core.py", line 1078, in main
rv = self.invoke(ctx)
^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/click/core.py", line 1434, in invoke
return ctx.invoke(self.callback, **ctx.params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/click/core.py", line 783, in invoke
return __callback(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/uvicorn/main.py", line 403, in main
run(
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/uvicorn/main.py", line 568, in run
server.run()
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/uvicorn/server.py", line 59, in run
return asyncio.run(self.serve(sockets=sockets))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/asyncio/runners.py", line 190, in run
return runner.run(main)
^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/asyncio/runners.py", line 118, in run
return self._loop.run_until_complete(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/asyncio/base_events.py", line 653, in run_until_complete
return future.result()
^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/uvicorn/server.py", line 66, in serve
config.load()
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/uvicorn/config.py", line 471, in load
self.loaded_app = import_from_string(self.app)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/uvicorn/importer.py", line 21, in import_from_string
module = importlib.import_module(module_str)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib/python3.11/importlib/init.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "", line 1206, in _gcd_import
File "", line 1178, in _find_and_load
File "", line 1149, in _find_and_load_unlocked
File "", line 690, in _load_unlocked
File "", line 940, in exec_module
File "", line 241, in _call_with_frames_removed
File "/home/martin/src/chatgpt-memory/rest_api.py", line 28, in
memory_manager = MemoryManager(datastore=redis_datastore, embed_client=embed_client, topk=1)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/chatgpt_memory/memory/manager.py", line 34, in init
Memory(conversation_id=conversation_id) for conversation_id in datastore.get_all_conversation_ids()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/chatgpt_memory/datastore/redis.py", line 132, in get_all_conversation_ids
result_documents = self.redis_connection.ft().search(query).docs
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/redis/commands/search/commands.py", line 420, in search
res = self.execute_command(SEARCH_CMD, *args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/redis/client.py", line 1269, in execute_command
return conn.retry.call_with_retry(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/redis/retry.py", line 46, in call_with_retry
return do()
^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/redis/client.py", line 1270, in
lambda: self._send_command_parse_response(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/redis/client.py", line 1246, in _send_command_parse_response
return self.parse_response(conn, command_name, **options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/redis/client.py", line 1286, in parse_response
response = connection.read_response()
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/martin/src/chatgpt-memory/gpt-memory/lib/python3.11/site-packages/redis/connection.py", line 905, in read_response
raise response
redis.exceptions.ResponseError: Unknown Index name

Regarding tiktoken, ChatGPT pointed out to me that there is an attribute 'use_tiktoken' in the class 'EmbeddingConfig' of chatgpt_memory/llm_client/openai/embedding/config.py. Setting it to 'True' does the trick....

For the Unknown Index name I don't have a solution yet. In redis.py there is the function "create_index()", but neither an index name is taken from a config file, nor is it directly in the code, and I have not yet been able to find out which index is expected or queried... I installed a Redis-Server on my own VPS / Laptop (Server: v5:7.0.11-1). The naked redis server is not enough and leads to an error, it needs the redisearch module(v1:1.2.2-4). Unfortunately even that is not enough. I was not yet able to identify what it is(it results in the 'Unknown Index name' error). When using the Redis cloud solution it works so far.

from chatgpt-memory.

Installing the Debian redis-stack-server package from the Redis repository on my Debian 12 system solved the problem for me. I haven't figured out how to disable the modules individually to see what is really needed. Somehow the server ignores the configuration file that is passed to it via the systemd service file. Lets see when I will get back to it again.

from chatgpt-memory.

Hi, thanks a lot for your interest in the project.

Due to time constraints, we are unable to continue development on this repository.

Please check out OpenAI's official retrieval plugin, offering similar functionality and active development: openai/chatgpt-retrieval-plugin

from chatgpt-memory.